Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1662592 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5018. Min Act: -0.0000

Data Index: 333482 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5400. Min Act: -0.0000

Data Index: 258724 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1391583 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1494175 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1356325 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4582. Min Act: -0.0000

Data Index: 710858 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1860555 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1974871 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1485541 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1593035 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4251. Min Act: -0.0000

Data Index: 435331 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1066467 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4377. Min Act: -0.0000

Data Index: 840722 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4350. Min Act: -0.0000

Data Index: 778195 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4337. Min Act: -0.0000

Data Index: 258878 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4443. Min Act: -0.0000

Data Index: 768843 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4189. Min Act: -0.0000

Data Index: 149136 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4169. Min Act: -0.0000

Data Index: 952064 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1474123 (The Pile)

Max Activating Token Index: 786